orchestrate

Produce a structured delegation plan for parallel agent execution. Takes a task description or plan output, analyzes dependencies, assigns agents, and groups tasks for parallel execution. Use after /plan-task or when you need to plan how to delegate work across agents.

6 stars

Best use case

orchestrate is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Produce a structured delegation plan for parallel agent execution. Takes a task description or plan output, analyzes dependencies, assigns agents, and groups tasks for parallel execution. Use after /plan-task or when you need to plan how to delegate work across agents.

Teams using orchestrate should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/orchestrate/SKILL.md --create-dirs "https://raw.githubusercontent.com/yu-iskw/llmops-demo-ts/main/.claude/skills/orchestrate/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/orchestrate/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How orchestrate Compares

Feature / AgentorchestrateStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Produce a structured delegation plan for parallel agent execution. Takes a task description or plan output, analyzes dependencies, assigns agents, and groups tasks for parallel execution. Use after /plan-task or when you need to plan how to delegate work across agents.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Orchestrate

Produce a structured delegation plan for the following:

$ARGUMENTS

## Instructions

1. **Read the input**: If a task plan is provided, analyze its tasks and dependencies. If only a description is provided, first break down the work, then plan delegation.
2. **Research the codebase**: Explore relevant files to understand what agents will need to work with.
3. **Assign agents**: Match each task to the best-suited agent based on expertise.
4. **Group for parallelism**: Identify which tasks can run in parallel (no shared file edits, no dependencies between them).
5. **Order by dependencies**: Tasks that depend on others go in later groups.
6. **Output the delegation plan**: Use the structured format below.

## Output Format

```text
## Delegation Plan

### Overview
[One sentence summary]

### Parallel Group 1: [Name]
Dependencies: none

| Task | Agent | Description | Files |
|------|-------|-------------|-------|
| 1.1 | [agent-name] | [What to do] | [Which files] |

### Parallel Group 2: [Name]
Dependencies: Group 1

| Task | Agent | Description | Files |
|------|-------|-------------|-------|
| 2.1 | [agent-name] | [What to do] | [Which files] |

### Quality Gates
- [ ] [What must pass]
```

## Rules

- NEVER execute tasks — only plan the delegation
- Maximize parallelism by grouping independent tasks
- Never assign two agents to edit the same file in the same parallel group
- Always schedule review agents (code-reviewer, qa, security) after implementation agents
- Be specific about which files each agent should work with

Related Skills

write-tests

6
from yu-iskw/llmops-demo-ts

Write unit tests, integration tests, or E2E tests for code. Use after implementing a feature or when test coverage is needed.

write-requirements

6
from yu-iskw/llmops-demo-ts

Write user stories, acceptance criteria, and technical requirements for a feature or change. Use when defining what needs to be built.

security-audit

6
from yu-iskw/llmops-demo-ts

Perform a security audit of the codebase. Checks for OWASP Top 10, AI-specific vulnerabilities, dependency issues, and configuration problems.

review-code

6
from yu-iskw/llmops-demo-ts

Review code changes for quality, security, and adherence to project conventions. Use after making code changes or when reviewing a pull request.

research

6
from yu-iskw/llmops-demo-ts

Research and gather reliable information about libraries, APIs, specifications, and best practices. Use when you need to understand external documentation before planning or implementing a feature.

plan-task

6
from yu-iskw/llmops-demo-ts

Create a structured implementation plan for a feature, refactoring, or multi-step task. Use as the first step in the pipeline before /orchestrate. Produces a plan that the orchestrator can turn into a delegation plan.

implement-feature

6
from yu-iskw/llmops-demo-ts

Implement a feature or fix a bug following the project's TypeScript patterns and conventions. Use when code changes are needed.

design-component

6
from yu-iskw/llmops-demo-ts

Design a UI component with specifications for layout, states, interactions, and accessibility. Use when creating new Vue.js components or redesigning existing ones.

deploy

6
from yu-iskw/llmops-demo-ts

Deploy the application or manage infrastructure. Handles Docker builds, CI/CD, and deployment workflows.

compliance-check

6
from yu-iskw/llmops-demo-ts

Check license compatibility, data privacy compliance, and AI ethics. Use when adding dependencies, handling user data, or reviewing regulatory requirements.

bump-dependencies

6
from yu-iskw/llmops-demo-ts

Bump or upgrade declared dependency versions in this pnpm workspace (root and packages/* package.json), with supply-chain checks before and after install. Use when the user asks to upgrade, bump, or refresh npm dependencies in manifests—not only the lockfile.

orchestrate-batch-refactor

31392
from sickn33/antigravity-awesome-skills

Plan and execute large refactors with dependency-aware work packets and parallel analysis.